Abstract
We demonstrate how Bayes linear methods, based on partial prior specifications, bring us quickly to the heart of otherwise complex problems, giving us natural and systematic tools for evaluating our analyses which are not readily available in the usual Bayes formalism. We illustrate the approach using an example concerning problems of prediction in a large brewery. We describe the computer language [B/D] (an acronym for beliefs adjusted by data), which implements the approach. [B/D] incorporates a natural graphical representation of the analysis, providing a powerful way of thinking about the process of knowledge formulation and criticism which is also accessible to non-technical users.
Similar content being viewed by others
References
de Finetti, B. (1974) Theory of Probability, vol. 1. Wiley, New York.
Farrow, M. and Goldstein, M. (1993) Bayes linear methods for grouped multivariate repeated measurement studies with application to crossover trials. Biometrika, 80, 39–59.
Farrow, M. and Spiropoulos, T. (1982) Graphical partial belief representation and linear bayes prediction for management. Technical Report 92-9, University of Sunderland, School of Computing and Information Systems, occasional paper.
Goldstein, M. (1986) Separating beliefs. In Bayesian Inference and Decision Techniques, P. Goel and A. Zellner (eds.), North Holland, Amsterdam.
Goldstein, M. (1987) Can we build a subjectivist statistical package? In Probability and Bayesian Statistics, R. Viertl (ed.), pp. 203–17. Plenum, New York.
Goldstein, M. (1988) The data trajectory. In Bayesian Statistics 3, J.-M. Bernardo et al. (eds.), pp. 189–209. Oxford University Press.
Goldstein, M. (1990) Influence and belief adjustment. In Influence Diagrams, Belief Nets and Decision Analysis, J. Smith and R. Oliver (eds.), Wiley, Chichester.
Goldstein, M. (1991) Belief transforms and the comparison of hypotheses. Annals of Statistics 19, 2067–89.
Goldstein, M. (1992) Bayes linear methods I—Adjusting beliefs: concepts and properties. Technical report, Department of Mathematical Sciences, University of Durham.
Goldstein, M. (1994) Revising exchangeable beliefs: subjectivist foundations for the inductive argument. In Aspects of Uncertainty: A Tribute to D. V. Lindley, P. Freeman and A. Smith (eds.), Wiley, Chichester.
Goldstein, M. and Wooff, D. (1994) Robustness measures for Bayes linear analyses. Journal of Statistical Planning and Inference, 40, 261–77.
Goldstein, M., Farrow, M. and Spiropoulos, T. (1993) Prediction under the influence: Bayes linear influence diagrams for prediction in a large brewery. The Statistician, 42, 445–59.
Spiropoulos, T. (1992) The development of a graphical object-oriented system for decision support in a manufacturing environment. Technical report, Sunderland Polytechnic Advanced Manufacturing Technology Conference 1992.
Wooff, D. (1992a) Bayes linear methods II—An example with an introduction to [B/D]. Technical report, Department of Mathematical Sciences, University of Durham.
Wooff, D. (1992b) [B/D] works. Bayesian Statistics 4, In J.-M. Bernardo et al. (eds.), pp. 851–9. Oxford University Press.
Wooff, D. (1994) [B/D] Manual. Technical report, Department of Mathematical Sciences, University of Durham.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Goldstein, M., Wooff, D.A. Bayes linear computation: concepts, implementation and programs. Stat Comput 5, 327–341 (1995). https://doi.org/10.1007/BF00162506
Issue Date:
DOI: https://doi.org/10.1007/BF00162506